About

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Datasets

Greatest papers with code

Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation

ECCV 2020 tensorflow/models

We view this work as a notable step towards building a simple procedure to harness unlabeled video sequences and extra images to surpass state-of-the-art performance on core computer vision tasks.

OPTICAL FLOW ESTIMATION PANOPTIC SEGMENTATION PATCH MATCHING SCENE SEGMENTATION

Continuous 3D Label Stereo Matching using Local Expansion Moves

28 Mar 2016t-taniai/LocalExpStereo

The local expansion moves extend traditional expansion moves by two ways: localization and spatial propagation.

PATCH MATCHING STEREO MATCHING STEREO MATCHING HAND

SOLAR: Second-Order Loss and Attention for Image Retrieval

ECCV 2020 tonyngjichun/SOLAR

One is focused on second-order spatial information to increase the performance of image descriptors, both local and global.

IMAGE RETRIEVAL PATCH MATCHING

L2-Net: Deep Learning of Discriminative Patch Descriptor in Euclidean Space

CVPR 2017 yuruntian/L2-Net

In this paper, we propose to learn high per- formance descriptor in Euclidean space via the Convolu- tional Neural Network (CNN).

PATCH MATCHING

Semi-Supervised Learning for Face Sketch Synthesis in the Wild

12 Dec 2018chaofengc/Face-Sketch-Wild

Instead of supervising the network with ground truth sketches, we first perform patch matching in feature space between the input photo and photos in a small reference set of photo-sketch pairs.

FACE SKETCH SYNTHESIS PATCH MATCHING

A Large Dataset for Improving Patch Matching

4 Jan 2018rmitra/PS-Dataset

Similarly on the Strecha dataset, we see an improvement of 3-5% for the matching task in non-planar scenes.

PATCH MATCHING

HyNet: Learning Local Descriptor with Hybrid Similarity Measure and Triplet Loss

NeurIPS 2020 yuruntian/HyNet

Recent works show that local descriptor learning benefits from the use of L2 normalisation, however, an in-depth analysis of this effect lacks in the literature.

3D RECONSTRUCTION PATCH MATCHING

Person Re-Identification via Recurrent Feature Aggregation

23 Jan 2017daodaofr/caffe-re-id

We address the person re-identification problem by effectively exploiting a globally discriminative feature representation from a sequence of tracked human regions/patches.

PATCH MATCHING PERSON RE-IDENTIFICATION